Deep Learning Stack Ensemble to Detect Sarcasm in News Headline Dataset
Stack Ensemble Deep Learning untuk Mendeteksi Sarkasme pada Dataset News Headline
DOI:
https://doi.org/10.21070/ups.689Keywords:
Sentiment Analysis, BiGRU, CNNs, LightGBM, Detection SarcasmeAbstract
Sarcasm is still often used by society to make someone give up and hurt. Detecting sarcasm is a tricky problem that remains in recent sentiment analysis studies. Sentiment analysis was carried out to classify sarcasm sentences that contain positivesentiments but have negative meanings. This study aims to compare the performance of three deep learning methods, namely Bidirectional Gated Recurrent Unit, Convolutional Neural Network, and LightGBM in detecting sarcasm in news headlines. The dataset used is from the Kaggle website and contains news headlines in English. The results showed that the LightGBM method had the best performance with an accuracy value of 91.2% and an f1 score of 90.2%, compared to the Bidirectional Gated Recurrent Unit and Convolutional Neural Network methods. Therefore, from the explanation above, it can be concluded that the LightGBM method is the best solution for detecting sarcasm.
Downloads
References
A. Heru, “Gaya Bahasa Sindiran Ironi, Sinisme Dan Sarkasme Dalam Berita Utama Harian Kompas,” J. Pembahsi (Pembelajaran Bhs. Dan Sastra Indones., vol. 8, no. 2, p. 43,2018.
S. Poria, E. Cambria, D. Hazarika, and P. Vij, “A deeper look into sarcastic tweets using deep convolutional neural networks,” COLING 2016 - 26th Int. Conf. Comput. Linguist. Proc. COLING 2016 Tech. Pap., pp. 1601–1612, 2016.
V. Govindan and V. Balakrishnan, “A machine learning approach in analysing the effect of hyperboles using negative sentiment tweets for sarcasm detection,” J. King Saud Univ. -Comput. Inf. Sci., vol. 34, no. 8, pp. 5110–5120, 2022.
S. M. Sarsam, H. Al-Samarraie, A. I. Alzahrani, and B. Wright, “Sarcasm detection using machine learning algorithms in Twitter: A systematic review,” Int. J. Mark. Res., vol. 62, no. 5,pp. 578–598, 2020.
D. Alita and A. R. Isnain, “Pendeteksian Sarkasme pada Proses Analisis Sentimen Menggunakan Random Forest Classifier,” J. Komputasi, vol. 8, no. 2, pp. 50–58, 2020.
M. S. Razali, A. A. Halin, L. Ye, S. Doraisamy, and N. M. Norowi, “Sarcasm Detection Using Deep Learning with Contextual Features,” IEEE Access, vol. 9, pp. 68609–68618, 2021.
Y. Yunitasari, A. Musdholifah, and A. K. Sari, “Sarcasm Detection For Sentiment Analysis in Indonesian Tweets,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 13, no. 1, p. 53, 2019.
K. S. Ranti and A. S. Girsang, “Indonesian sarcasm detection using convolutional neural network,” Int. J. Emerg. Trends Eng. Res., vol. 8, no. 9, pp. 4952–4955, 2020.
S. Fanissa, M. A. Fauzi, and S. Adinugroho, “Analisis Sentimen Pariwisata di Kota Malang Menggunakan Metode Naive Bayes dan Seleksi Fitur Query Expansion Ranking,” Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 8, pp. 2766–2770, 2018.
C. Jia and H. Zan, “Context-Based Sarcasm Detection Model in Chinese Social Media Using BERT and Bi-GRU Models,” CEUR Workshop Proc., vol. 3150, pp. 42–50, 2022.
H. F. Fadli and A. F. Hidayatullah, “Identifikasi Cyberbullying Pada Media Sosial Twitter Menggunakan Metode Klasifikasi Random Forest,” Automata, 2019.
M. A. Rosid, D. Siahaan, and A. Saikhu, “Pre-Trained Word Embeddings for Sarcasm Detection in Indonesian Tweets: A Comparative Study,” in 2022 9th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), 2022, pp. 281–286.
C. N. N. Bigru, “applied sciences Short Text Aspect-Based Sentiment Analysis Based on,” 2022.
P. Mehndiratta, S. Sachdeva, and D. Soni, “Detection of sarcasm in text data using deep convolutional neural networks,” Scalable Comput., vol. 18, no. 3, pp. 219–228, 2017.
D. D. Rufo, T. G. Debelee, A. Ibenthal, and W. G. Negera, “Diagnosis of diabetes mellitus using gradient boosting machine (Lightgbm),” Diagnostics, vol. 11, no. 9, pp. 1–14, 2021.
Downloads
Additional Files
Posted
License
Copyright (c) 2023 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
